You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ASR (Automatic Speech Recognition) can convert audio to text, but it's not suitable for all scenarios.
For example, in the text "D7851次列车制动," the letter 'D' should be pronounced the same as the last character '动 (dong, 4th tone).'
I can't simply increase the weight of the word 'D' when receiving audio input pronounced as 'dong (4th tone).'
I'm considering introducing a Language Model (LM) into the final step of ASR (text generation) to automatically correct the output text.
What I've found in this project that may help me:
There are two classes named 'OnlineLMConfig' and 'OfflineLMConfig,' which seem to be helpful.
The documentation lacks details for both 'OnlineLMConfig' and 'OfflineLMConfig,' so I'm uncertain if they will truly solve my problem.
My suggestions:
Provide multi-programming-language support for XXLMConfig.
Include usage instructions for XXLMConfig in the documentation or provide sample codes.
Provide a simple, standard LM as a sample, similar to how VAD (Voice Activity Detection) was introduced into non-streaming ASR.
The text was updated successfully, but these errors were encountered:
fengzhi09
changed the title
ASR Improve With LM:provide LMConfig muti-program-lanuage support and usage in the doc or sample codes
ASR Improve With XXLMConfig:muti-program-lanuage support ,usage in the doc or sample codes
Dec 3, 2024
Background:
For example, in the text "D7851次列车制动," the letter 'D' should be pronounced the same as the last character '动 (dong, 4th tone).'
What I've found in this project that may help me:
There are two classes named 'OnlineLMConfig' and 'OfflineLMConfig,' which seem to be helpful.
You can create instances of both classes in Java, but only 'OfflineLMConfig' is available in .NET(dotnet)or c-api.
https://github.com/k2-fsa/sherpa-onnx/blob/master/sherpa-onnx/c-api/c-api.h#L117
https://github.com/k2-fsa/sherpa-onnx/blob/master/sherpa-onnx/c-api/c-api.h#L440
The documentation lacks details for both 'OnlineLMConfig' and 'OfflineLMConfig,' so I'm uncertain if they will truly solve my problem.
My suggestions:
The text was updated successfully, but these errors were encountered: